表面纵裂纹是铸坯质量缺陷中一种最常见的表面质量缺陷。环境因素使得铸坯表面纵裂纹在线检测精度不高,各大钢厂铸坯质检仍要依赖人工,因此提出一种基于粒子群PSO优化概率神经网络PNN的铸坯全长表面纵裂纹预测方法。首先,建立铸坯生产过程跟踪及数据时空变换模型,构建铸坯生产系统将生产过程数据与铸坯长度方向进行匹配;再利用PNN的Bayes 最小风险准则进行有监督特征学习,并利用寻优算法PSO优化PNN关键参数的选取,得到最终的模型PSO-PNN;最后,利用某钢厂连铸产线铸坯质量缺陷数据和生产过程数据进行试验验证。结果表明,该方法对铸坯整体的质量预测分类精度达到97.5%,铸坯全长的裂纹缺陷的预测精确率和召回率均在92%以上,能有效实现铸坯全长表面纵裂纹的预测,为现场质检人员提供参考。
Abstract
Surface longitudinal crack is one of the most common surface defects on continuous casting slabs. Due to environmental factors, the on-line detection accuracy of longitudinal cracks on the surface of casting slab is not high, and the quality inspection of casting slab in major steel mills still depends on manual work. Therefore, a method of predicting longitudinal cracks on the surface of casting slab based on particle swarm optimization probabilistic neural network PNN is proposed. Firstly, continuous casting production process tracking and data time-space transformation was established to match the production process data with the slab on length direction. The Bayes minimum risk criterion of PNN was used for supervised feature learning, and the optimization algorithm PSO was used to optimize the selection of key parameters of PNN, and the final model PSO-PNN was obtained. Finally, the quality defect data and production process data of continuous casting line in a steel mill are used for experimental verification. The results show that the classification accuracy of the method is 97.5% for the whole slab and precision and recall for surface longitudinal crack of slab on length direction are above 92%, which can effectively realize the prediction of the longitudinal cracks on the surface of the full length of the slab, and provide a reference for on-site quality inspection personnel.
关键词
全长表面纵裂纹预测 /
铸坯生产过程跟踪 /
数据时空变换 /
概率神经网络(PNN) /
粒子群优化算法(PSO)
{{custom_keyword}} /
Key words
prediction for the surface longitudinal crack on length direction /
continuous casting production process tracking /
data time-space transformation /
probabilistic neural network (PNN) /
particle swarm optimization (PSO)
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 蔡开科.钢洁净度控制[C]//第十届全国炼钢学术会议论文集.北京: 中国金属学会炼钢分会,1998:70.
[2] 蔡开科.现代连铸技术进展[M].北京:冶金工业出版社,2003.
[3] 徐科,周鹏,邓能辉. 高温铸坯表面在线检测技术的开发与应用[C]//2014年全国炼钢—连铸生产技术会论文集. 唐山: 全国炼钢—连铸生产技术会,2014:421.
[4] 杨秉俭,刘伟涛,苏俊义.薄板坯连铸结晶器中铸坯凝固壳应力发展的有限元分析[J].应用力学学报,1994(2):55.
[5] 荆德君,蔡开科.连铸结晶器内铸坯温度场和应力场耦合过程数值模拟[J].北京科技大学学报,2000(5):417.
[6] DU F,WANG X,LIU Y, et al. Prediction of longitudinal cracks based on a full-scale finite-element model coupled inverse algorithm for a continuously cast slab[J]. Steel Research International, 2017(10):88.
[7] 王宁,王旭东,蔡来强,等.基于无网格伽辽金法的连铸坯凝固计算方法[J].工程科学学报,2020,42(2):186.
[8] Preissl H, Faster T. Automatic quality control of cast slabs at the VOEST-ALPINE steel works[C]//Steelmaking Conference Proceedings. Iron and Steel Society,1995:621.
[9] Normanton A S, Barber B.Developments in online surface and internal quality forecasting of continuously cast semis[J].Ironmaking and Steelmaking, 2004,31(5): 377.
[10] 姜广森.连铸板坯表面质量预报专家系统的研究[D]. 武汉:武汉科技大学,2005.
[11] 王悦新,邱以清,刘相华.连铸坯质量判定模糊专家系统[J].东北大学学报(自然科学版),2009,30(7):989.
[12] 常运合,张家泉,张家泉,等.基于BP神经网络的大方坯质量在线预报模型[J].钢铁,2011,46(5):33.
[13] 陈恒志,杨建平,卢新春,等.基于极限学习机(ELM)的连铸坯质量预测[J].工程科学学报,2018,40(7):815.
[14] 白蕊.随机森林算法在铸坯内部缺陷预测中研究与应用[D]. 北京:北京科技大学,2018.
[15] 邵健,何安瑞,董光德,等.基于工业互联的钢铁全流程质量管控系统[J].冶金自动化,2020,44(01):8.
[16] 孙丹,钱宏智,王胜东,等.连铸坯质量预测专家系统的研发与应用[J].矿冶,2013,22(增刊1):194.
[17] 米进周,傅磊,赵静.承钢连铸物料跟踪系统的应用[J].重型机械,2010(增刊2):239.
[18] 奥特斯.钢冶金学[M].北京:冶金工业出版社,1997:3.
[19] 毕经汉,唐萍,文光华,等.异钢种连浇交接坯长度与位置预测模型[J].过程工程学报,2012,12(2):271.
[20] Hinton G, Osindero S. A fast learning algorithm for deep belief nets[J]. Neural Comput, 2006,18 (7):1527.
[21] Kennedy J,Eberhart R. Particle swarm optimization[C]//Proceedings of IEEE International Conference on Neural Networks. Pisca-taway, NJ:IEEE Service Center, 1995: 1942.
[22] Shi Y, Eberhart R. Empirical study of particle swarm optimization[C]//Proceedings of the IEEE CEC, 1990:1945.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
基金
国家自然科学基金资助项目(61903031)
{{custom_fund}}
PDF(4835 KB)
